ACL 2022long25 citations

Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings

Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yufei Huang, Guojiang Zhao, Yue Zhang, Stan Li

Abstract

Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due to their low computational cost, ease of deployment, and stability. In this paper, we aim to improve word embeddings by 1) incorporating more contextual information from existing pre-trained models into the Skip-gram framework, which we call Context-to-Vec; 2) proposing a post-processing retrofitting method for static embeddings independent of training by employing priori synonym knowledge and weighted vector distribution. Through extrinsic and intrinsic tasks, our methods are well proven to outperform the baselines by a large margin.

BibTeX
@inproceedings{zheng-etal-2022-using,
    title = "Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings",
    author = "Zheng, Jiangbin  and
      Wang, Yile  and
      Wang, Ge  and
      Xia, Jun  and
      Huang, Yufei  and
      Zhao, Guojiang  and
      Zhang, Yue  and
      Li, Stan",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.561/",
    doi = "10.18653/v1/2022.acl-long.561",
    pages = "8154--8163"
}